BibBase balestriero, r

generated by

Group by
- Year
- Author
- Type
- Keyword
- Downloads

2024 (5)

Understanding the detrimental class-level effects of data augmentation. Kirichenko, P.; Ibrahim, M.; Balestriero, R.; Bouchacourt, D.; Vedantam, S. R.; Firooz, H.; and Wilson, A. G Advances in Neural Information Processing Systems, 36. 2024.
link bibtex

@article{kirichenko2024understanding,
  title={Understanding the detrimental class-level effects of data augmentation},
  author={Kirichenko, Polina and Ibrahim, Mark and Balestriero, Randall and Bouchacourt, Diane and Vedantam, Shanmukha Ramakrishna and Firooz, Hamed and Wilson, Andrew G},
  journal={Advances in Neural Information Processing Systems},
  volume={36},
  year={2024}
}

An Information Theory Perspective on Variance-Invariance-Covariance Regularization. Shwartz-Ziv, R.; Balestriero, R.; Kawaguchi, K.; Rudner, T. G.; and LeCun, Y. Advances in Neural Information Processing Systems, 36. 2024.
link bibtex

@article{shwartz2024information,
  title={An Information Theory Perspective on Variance-Invariance-Covariance Regularization},
  author={Shwartz-Ziv, Ravid and Balestriero, Randall and Kawaguchi, Kenji and Rudner, Tim GJ and LeCun, Yann},
  journal={Advances in Neural Information Processing Systems},
  volume={36},
  year={2024}
}

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning. Feizi, A.; Balestriero, R.; Romero-Soriano, A.; and Rabbany, R. arXiv preprint arXiv:2401.01990. 2024.
link bibtex

@article{feizi2024gps,
  title={GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning},
  author={Feizi, Aarash and Balestriero, Randall and Romero-Soriano, Adriana and Rabbany, Reihaneh},
  journal={arXiv preprint arXiv:2401.01990},
  year={2024}
}

Learning by Reconstruction Produces Uninformative Features For Perception. Balestriero, R.; and LeCun, Y. arXiv preprint arXiv:2402.11337. 2024.
link bibtex

@article{balestriero2024learning,
  title={Learning by Reconstruction Produces Uninformative Features For Perception},
  author={Balestriero, Randall and LeCun, Yann},
  journal={arXiv preprint arXiv:2402.11337},
  year={2024}
}

Deep Networks Always Grok and Here is Why. Humayun, A. I.; Balestriero, R.; and Baraniuk, R. arXiv preprint arXiv:2402.15555. 2024.
link bibtex

@article{humayun2024deep,
  title={Deep Networks Always Grok and Here is Why},
  author={Humayun, Ahmed Imtiaz and Balestriero, Randall and Baraniuk, Richard},
  journal={arXiv preprint arXiv:2402.15555},
  year={2024}
}

2023 (19)

Singular value perturbation and deep network optimization. Riedi, R. H; Balestriero, R.; and Baraniuk, R. G Constructive Approximation, 57(2): 807–852. 2023.
link bibtex

@article{riedi2023singular,
  title={Singular value perturbation and deep network optimization},
  author={Riedi, Rudolf H and Balestriero, Randall and Baraniuk, Richard G},
  journal={Constructive Approximation},
  volume={57},
  number={2},
  pages={807--852},
  year={2023},
  publisher={Springer US New York}
}

Rankme: Assessing the downstream performance of pretrained self-supervised representations by their rank. Garrido, Q.; Balestriero, R.; Najman, L.; and Lecun, Y. In International Conference on Machine Learning, pages 10929–10974, 2023. PMLR
link bibtex

@inproceedings{garrido2023rankme,
  title={Rankme: Assessing the downstream performance of pretrained self-supervised representations by their rank},
  author={Garrido, Quentin and Balestriero, Randall and Najman, Laurent and Lecun, Yann},
  booktitle={International Conference on Machine Learning},
  pages={10929--10974},
  year={2023},
  organization={PMLR}
}

POLICE: Provably optimal linear constraint enforcement for deep neural networks. Balestriero, R.; and LeCun, Y. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5, 2023. IEEE
link bibtex

@inproceedings{balestriero2023police,
  title={POLICE: Provably optimal linear constraint enforcement for deep neural networks},
  author={Balestriero, Randall and LeCun, Yann},
  booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={1--5},
  year={2023},
  organization={IEEE}
}

On minimal variations for unsupervised representation learning. Cabannes, V.; Bietti, A.; and Balestriero, R. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5, 2023. IEEE
link bibtex

@inproceedings{cabannes2023minimal,
  title={On minimal variations for unsupervised representation learning},
  author={Cabannes, Vivien and Bietti, Alberto and Balestriero, Randall},
  booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={1--5},
  year={2023},
  organization={IEEE}
}

The ssl interplay: Augmentations, inductive bias, and generalization. Cabannes, V.; Kiani, B.; Balestriero, R.; LeCun, Y.; and Bietti, A. In International Conference on Machine Learning, pages 3252–3298, 2023. PMLR
link bibtex

@inproceedings{cabannes2023ssl,
  title={The ssl interplay: Augmentations, inductive bias, and generalization},
  author={Cabannes, Vivien and Kiani, Bobak and Balestriero, Randall and LeCun, Yann and Bietti, Alberto},
  booktitle={International Conference on Machine Learning},
  pages={3252--3298},
  year={2023},
  organization={PMLR}
}

Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head. Balestriero, R. arXiv preprint arXiv:2302.10260. 2023.
link bibtex

@article{balestriero2023unsupervised,
  title={Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head},
  author={Balestriero, Randall},
  journal={arXiv preprint arXiv:2302.10260},
  year={2023}
}

Splinecam: Exact visualization and characterization of deep network geometry and decision boundaries. Humayun, A. I.; Balestriero, R.; Balakrishnan, G.; and Baraniuk, R. G In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3789–3798, 2023.
link bibtex

@inproceedings{humayun2023splinecam,
  title={Splinecam: Exact visualization and characterization of deep network geometry and decision boundaries},
  author={Humayun, Ahmed Imtiaz and Balestriero, Randall and Balakrishnan, Guha and Baraniuk, Richard G},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={3789--3798},
  year={2023}
}

Fair-ensemble: When fairness naturally emerges from deep ensembling. Ko, W.; D'souza, D.; Nguyen, K.; Balestriero, R.; and Hooker, S. arXiv preprint arXiv:2303.00586. 2023.
link bibtex

@article{ko2023fair,
  title={Fair-ensemble: When fairness naturally emerges from deep ensembling},
  author={Ko, Wei-Yin and D'souza, Daniel and Nguyen, Karina and Balestriero, Randall and Hooker, Sara},
  journal={arXiv preprint arXiv:2303.00586},
  year={2023}
}

Towards democratizing joint-embedding self-supervised learning. Bordes, F.; Balestriero, R.; and Vincent, P. arXiv preprint arXiv:2303.01986. 2023.
link bibtex

@article{bordes2023towards,
  title={Towards democratizing joint-embedding self-supervised learning},
  author={Bordes, Florian and Balestriero, Randall and Vincent, Pascal},
  journal={arXiv preprint arXiv:2303.01986},
  year={2023}
}

Understanding the class-specific effects of data augmentations. Kirichenko, P.; Balestriero, R.; Ibrahim, M.; Vedantam, S. R.; Firooz, H.; and Wilson, A. G. In ICLR 2023 Workshop on Pitfalls of limited data and computation for Trustworthy ML, 2023.
link bibtex

@inproceedings{kirichenko2023understanding,
  title={Understanding the class-specific effects of data augmentations},
  author={Kirichenko, Polina and Balestriero, Randall and Ibrahim, Mark and Vedantam, Shanmukha Ramakrishna and Firooz, Hamed and Wilson, Andrew Gordon},
  booktitle={ICLR 2023 Workshop on Pitfalls of limited data and computation for Trustworthy ML},
  year={2023}
}

Active self-supervised learning: A few low-cost relationships are all you need. Cabannes, V.; Bottou, L.; Lecun, Y.; and Balestriero, R. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16274–16283, 2023.
link bibtex

@inproceedings{cabannes2023active,
  title={Active self-supervised learning: A few low-cost relationships are all you need},
  author={Cabannes, Vivien and Bottou, Leon and Lecun, Yann and Balestriero, Randall},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={16274--16283},
  year={2023}
}

A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation. Bordes, F.; Lavoie, S.; Balestriero, R.; Ballas, N.; and Vincent, P. arXiv preprint arXiv:2304.05369. 2023.
link bibtex

@article{bordes2023surprisingly,
  title={A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation},
  author={Bordes, Florian and Lavoie, Samuel and Balestriero, Randall and Ballas, Nicolas and Vincent, Pascal},
  journal={arXiv preprint arXiv:2304.05369},
  year={2023}
}

A cookbook of self-supervised learning. Balestriero, R.; Ibrahim, M.; Sobal, V.; Morcos, A.; Shekhar, S.; Goldstein, T.; Bordes, F.; Bardes, A.; Mialon, G.; Tian, Y.; and others arXiv preprint arXiv:2304.12210. 2023.
link bibtex

@article{balestriero2023cookbook,
  title={A cookbook of self-supervised learning},
  author={Balestriero, Randall and Ibrahim, Mark and Sobal, Vlad and Morcos, Ari and Shekhar, Shashank and Goldstein, Tom and Bordes, Florian and Bardes, Adrien and Mialon, Gregoire and Tian, Yuandong and others},
  journal={arXiv preprint arXiv:2304.12210},
  year={2023}
}

Fast and exact enumeration of deep networks partitions regions. Balestriero, R.; and LeCun, Y. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5, 2023. IEEE
link bibtex

@inproceedings{balestriero2023fast,
  title={Fast and exact enumeration of deep networks partitions regions},
  author={Balestriero, Randall and LeCun, Yann},
  booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={1--5},
  year={2023},
  organization={IEEE}
}

Martian time-series unraveled: A multi-scale nested approach with factorial variational autoencoders. Siahkoohi, A.; Morel, R.; Balestriero, R.; Allys, E.; Sainton, G.; Kawamura, T.; and de Hoop, M. V arXiv preprint arXiv:2305.16189. 2023.
link bibtex

@article{siahkoohi2023martian,
  title={Martian time-series unraveled: A multi-scale nested approach with factorial variational autoencoders},
  author={Siahkoohi, Ali and Morel, Rudy and Balestriero, Randall and Allys, Erwan and Sainton, Gr{\'e}gory and Kawamura, Taichi and de Hoop, Maarten V},
  journal={arXiv preprint arXiv:2305.16189},
  year={2023}
}

Provable Instance Specific Robustness via Linear Constraints. Humayun, A. I.; Casco-Rodriguez, J.; Balestriero, R.; and Baraniuk, R. In The Second Workshop on New Frontiers in Adversarial Machine Learning, 2023.
link bibtex

@inproceedings{humayun2023provable,
  title={Provable Instance Specific Robustness via Linear Constraints},
  author={Humayun, Ahmed Imtiaz and Casco-Rodriguez, Josue and Balestriero, Randall and Baraniuk, Richard},
  booktitle={The Second Workshop on New Frontiers in Adversarial Machine Learning},
  year={2023}
}

Training Dynamics of Deep Network Linear Regions. Humayun, A. I.; Balestriero, R.; and Baraniuk, R. arXiv preprint arXiv:2310.12977. 2023.
link bibtex

@article{humayun2023training,
  title={Training Dynamics of Deep Network Linear Regions},
  author={Humayun, Ahmed Imtiaz and Balestriero, Randall and Baraniuk, Richard},
  journal={arXiv preprint arXiv:2310.12977},
  year={2023}
}

Characterizing large language model geometry solves toxicity detection and generation. Balestriero, R.; Cosentino, R.; and Shekkizhar, S. arXiv preprint arXiv:2312.01648. 2023.
link bibtex

@article{balestriero2023characterizing,
  title={Characterizing large language model geometry solves toxicity detection and generation},
  author={Balestriero, Randall and Cosentino, Romain and Shekkizhar, Sarath},
  journal={arXiv preprint arXiv:2312.01648},
  year={2023}
}

Deep Network Partition Density Exhibits Double Descent. Humayun, A. I.; Balestriero, R.; and Baraniuk, R. . 2023.
link bibtex

@article{humayun2023deep,
  title={Deep Network Partition Density Exhibits Double Descent},
  author={Humayun, Ahmed Imtiaz and Balestriero, Randall and Baraniuk, Richard},
  year={2023}
}

2022 (19)

Interpretable and learnable super-resolution time-frequency representation. Balestriero, R.; Glotin, H.; and Baranuik, R. In Mathematical and Scientific Machine Learning, pages 118–152, 2022. PMLR
link bibtex

@inproceedings{balestriero2022interpretable,
  title={Interpretable and learnable super-resolution time-frequency representation},
  author={Balestriero, Randall and Glotin, Herv{\'e} and Baranuik, Richard},
  booktitle={Mathematical and Scientific Machine Learning},
  pages={118--152},
  year={2022},
  organization={PMLR}
}

No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds. Humayun, A. I.; Balestriero, R.; Kyrillidis, A.; and Baraniuk, R. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 4433–4437, 2022. IEEE
link bibtex

@inproceedings{humayun2022no,
  title={No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds},
  author={Humayun, Ahmed Imtiaz and Balestriero, Randall and Kyrillidis, Anastasios and Baraniuk, Richard},
  booktitle={ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={4433--4437},
  year={2022},
  organization={IEEE}
}

Spatial Transformer K-Means. Cosentino, R.; Balestriero, R.; Bahroun, Y.; Sengupta, A.; Baraniuk, R.; and Aazhang, B. In 2022 56th Asilomar Conference on Signals, Systems, and Computers, pages 1444–1448, 2022. IEEE
link bibtex

@inproceedings{cosentino2022spatial,
  title={Spatial Transformer K-Means},
  author={Cosentino, Romain and Balestriero, Randall and Bahroun, Yanis and Sengupta, Anirvan and Baraniuk, Richard and Aazhang, Behnaam},
  booktitle={2022 56th Asilomar Conference on Signals, Systems, and Computers},
  pages={1444--1448},
  year={2022},
  organization={IEEE}
}

Neuroview-rnn: It’s about time. Barberan, C.; Alemmohammad, S.; Liu, N.; Balestriero, R.; and Baraniuk, R. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pages 1683–1697, 2022.
link bibtex

@inproceedings{barberan2022neuroview,
  title={Neuroview-rnn: It’s about time},
  author={Barberan, CJ and Alemmohammad, Sina and Liu, Naiming and Balestriero, Randall and Baraniuk, Richard},
  booktitle={Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency},
  pages={1683--1697},
  year={2022}
}

Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values. Imtiaz Humayun, A.; Balestriero, R.; and Baraniuk, R. arXiv e-prints,arXiv–2203. 2022.
link bibtex

@article{imtiaz2022polarity,
  title={Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values},
  author={Imtiaz Humayun, Ahmed and Balestriero, Randall and Baraniuk, Richard},
  journal={arXiv e-prints},
  pages={arXiv--2203},
  year={2022}
}

projUNN: efficient method for training deep networks with unitary matrices. Kiani, B.; Balestriero, R.; LeCun, Y.; and Lloyd, S. Advances in Neural Information Processing Systems, 35: 14448–14463. 2022.
link bibtex

@article{kiani2022projunn,
  title={projUNN: efficient method for training deep networks with unitary matrices},
  author={Kiani, Bobak and Balestriero, Randall and LeCun, Yann and Lloyd, Seth},
  journal={Advances in Neural Information Processing Systems},
  volume={35},
  pages={14448--14463},
  year={2022}
}

The effects of regularization and data augmentation are class dependent. Balestriero, R.; Bottou, L.; and LeCun, Y. Advances in Neural Information Processing Systems, 35: 37878–37891. 2022.
link bibtex

@article{balestriero2022effects,
  title={The effects of regularization and data augmentation are class dependent},
  author={Balestriero, Randall and Bottou, Leon and LeCun, Yann},
  journal={Advances in Neural Information Processing Systems},
  volume={35},
  pages={37878--37891},
  year={2022}
}

Deeptensor: Low-rank tensor decomposition with deep network priors. Saragadam, V.; Balestriero, R.; Veeraraghavan, A.; and Baraniuk, R. G arXiv preprint arXiv:2204.03145. 2022.
link bibtex 7 downloads

@article{saragadam2022deeptensor,
  title={Deeptensor: Low-rank tensor decomposition with deep network priors},
  author={Saragadam, Vishwanath and Balestriero, Randall and Veeraraghavan, Ashok and Baraniuk, Richard G},
  journal={arXiv preprint arXiv:2204.03145},
  year={2022}
}

Deephull: Fast convex hull approximation in high dimensions. Balestriero, R.; Wang, Z.; and Baraniuk, R. G In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 3888–3892, 2022. IEEE
link bibtex

@inproceedings{balestriero2022deephull,
  title={Deephull: Fast convex hull approximation in high dimensions},
  author={Balestriero, Randall and Wang, Zichao and Baraniuk, Richard G},
  booktitle={ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={3888--3892},
  year={2022},
  organization={IEEE}
}

Contrastive and non-contrastive self-supervised learning recover global and local spectral embedding methods. Balestriero, R.; and LeCun, Y. Advances in Neural Information Processing Systems, 35: 26671–26685. 2022.
link bibtex

@article{balestriero2022contrastive,
  title={Contrastive and non-contrastive self-supervised learning recover global and local spectral embedding methods},
  author={Balestriero, Randall and LeCun, Yann},
  journal={Advances in Neural Information Processing Systems},
  volume={35},
  pages={26671--26685},
  year={2022}
}

What do we maximize in self-supervised learning?. Shwartz-Ziv, R.; Balestriero, R.; and LeCun, Y. arXiv preprint arXiv:2207.10081. 2022.
link bibtex

@article{shwartz2022we,
  title={What do we maximize in self-supervised learning?},
  author={Shwartz-Ziv, Ravid and Balestriero, Randall and LeCun, Yann},
  journal={arXiv preprint arXiv:2207.10081},
  year={2022}
}

Joint embedding self-supervised learning in the kernel regime. Kiani, B. T; Balestriero, R.; Chen, Y.; Lloyd, S.; and LeCun, Y. arXiv preprint arXiv:2209.14884. 2022.
link bibtex

@article{kiani2022joint,
  title={Joint embedding self-supervised learning in the kernel regime},
  author={Kiani, Bobak T and Balestriero, Randall and Chen, Yubei and Lloyd, Seth and LeCun, Yann},
  journal={arXiv preprint arXiv:2209.14884},
  year={2022}
}

Batch normalization explained. Balestriero, R.; and Baraniuk, R. G arXiv preprint arXiv:2209.14778. 2022.
link bibtex

@article{balestriero2022batch,
  title={Batch normalization explained},
  author={Balestriero, Randall and Baraniuk, Richard G},
  journal={arXiv preprint arXiv:2209.14778},
  year={2022}
}

Variance covariance regularization enforces pairwise independence in self-supervised representations. Mialon, G.; Balestriero, R.; and LeCun, Y. . 2022.
link bibtex

@article{mialon2022variance,
  title={Variance covariance regularization enforces pairwise independence in self-supervised representations},
  author={Mialon, Gr{\'e}goire and Balestriero, Randall and LeCun, Yann},
  year={2022}
}

The hidden uniform cluster prior in self-supervised learning. Assran, M.; Balestriero, R.; Duval, Q.; Bordes, F.; Misra, I.; Bojanowski, P.; Vincent, P.; Rabbat, M.; and Ballas, N. arXiv preprint arXiv:2210.07277. 2022.
link bibtex

@article{assran2022hidden,
  title={The hidden uniform cluster prior in self-supervised learning},
  author={Assran, Mahmoud and Balestriero, Randall and Duval, Quentin and Bordes, Florian and Misra, Ishan and Bojanowski, Piotr and Vincent, Pascal and Rabbat, Michael and Ballas, Nicolas},
  journal={arXiv preprint arXiv:2210.07277},
  year={2022}
}

Imagenet-x: Understanding model mistakes with factor of variation annotations. Idrissi, B. Y.; Bouchacourt, D.; Balestriero, R.; Evtimov, I.; Hazirbas, C.; Ballas, N.; Vincent, P.; Drozdzal, M.; Lopez-Paz, D.; and Ibrahim, M. arXiv preprint arXiv:2211.01866. 2022.
link bibtex

@article{idrissi2022imagenet,
  title={Imagenet-x: Understanding model mistakes with factor of variation annotations},
  author={Idrissi, Badr Youbi and Bouchacourt, Diane and Balestriero, Randall and Evtimov, Ivan and Hazirbas, Caner and Ballas, Nicolas and Vincent, Pascal and Drozdzal, Michal and Lopez-Paz, David and Ibrahim, Mark},
  journal={arXiv preprint arXiv:2211.01866},
  year={2022}
}

Exact visualization of deep neural network geometry and decision boundary. Humayun, A. I.; Balestriero, R.; and Baraniuk, R. In NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations, 2022.
link bibtex

@inproceedings{humayun2022exact,
  title={Exact visualization of deep neural network geometry and decision boundary},
  author={Humayun, Ahmed Imtiaz and Balestriero, Randall and Baraniuk, Richard},
  booktitle={NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations},
  year={2022}
}

A data-augmentation is worth a thousand samples: Analytical moments and sampling-free training. Balestriero, R.; Misra, I.; and LeCun, Y. Advances in Neural Information Processing Systems, 35: 19631–19644. 2022.
link bibtex

@article{balestriero2022data,
  title={A data-augmentation is worth a thousand samples: Analytical moments and sampling-free training},
  author={Balestriero, Randall and Misra, Ishan and LeCun, Yann},
  journal={Advances in Neural Information Processing Systems},
  volume={35},
  pages={19631--19644},
  year={2022}
}

Guillotine regularization: Why removing layers is needed to improve generalization in self-supervised learning. Bordes, F.; Balestriero, R.; Garrido, Q.; Bardes, A.; and Vincent, P. arXiv preprint arXiv:2206.13378. 2022.
link bibtex

@article{bordes2022guillotine,
  title={Guillotine regularization: Why removing layers is needed to improve generalization in self-supervised learning},
  author={Bordes, Florian and Balestriero, Randall and Garrido, Quentin and Bardes, Adrien and Vincent, Pascal},
  journal={arXiv preprint arXiv:2206.13378},
  year={2022}
}

2021 (14)

Provable finite data generalization with group autoencoder. Cosentino, R.; Balestriero, R.; Baraniuk, R.; and Aazhang, B. In Mathematical and Scientific Machine Learning, 2021.
link bibtex

@inproceedings{cosentino2021provable,
  title={Provable finite data generalization with group autoencoder},
  author={Cosentino, Romain and Balestriero, Randall and Baraniuk, Richard and Aazhang, Behnaam},
  booktitle={Mathematical and Scientific Machine Learning},
  year={2021}
}

Wearing a mask: Compressed representations of variable-length sequences using recurrent neural tangent kernels. Alemohammad, S.; Babaei, H.; Balestriero, R.; Cheung, M. Y; Humayun, A. I.; LeJeune, D.; Liu, N.; Luzi, L.; Tan, J.; Wang, Z.; and others In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2950–2954, 2021. IEEE
link bibtex

@inproceedings{alemohammad2021wearing,
  title={Wearing a mask: Compressed representations of variable-length sequences using recurrent neural tangent kernels},
  author={Alemohammad, Sina and Babaei, Hossein and Balestriero, Randall and Cheung, Matt Y and Humayun, Ahmed Imtiaz and LeJeune, Daniel and Liu, Naiming and Luzi, Lorenzo and Tan, Jasper and Wang, Zichao and others},
  booktitle={ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={2950--2954},
  year={2021},
  organization={IEEE}
}

Max-affine spline insights into deep network pruning. You, H.; Balestriero, R.; Lu, Z.; Kou, Y.; Shi, H.; Zhang, S.; Wu, S.; Lin, Y.; and Baraniuk, R. arXiv preprint arXiv:2101.02338. 2021.
link bibtex

@article{you2021max,
  title={Max-affine spline insights into deep network pruning},
  author={You, Haoran and Balestriero, Randall and Lu, Zhihan and Kou, Yutong and Shi, Huihong and Zhang, Shunyao and Wu, Shang and Lin, Yingyan and Baraniuk, Richard},
  journal={arXiv preprint arXiv:2101.02338},
  year={2021}
}

Observing seismic signatures of slow slip events with unsupervised learning. Seydoux, L.; Campillo, M.; Steinmann, R.; Balestriero, R.; and de Hoop, M. In EGU General Assembly Conference Abstracts, pages EGU21–5603, 2021.
link bibtex

@inproceedings{seydoux2021observing,
  title={Observing seismic signatures of slow slip events with unsupervised learning},
  author={Seydoux, Leonard and Campillo, Michel and Steinmann, Ren{\'e} and Balestriero, Randall and de Hoop, Maarten},
  booktitle={EGU General Assembly Conference Abstracts},
  pages={EGU21--5603},
  year={2021}
}

Fast Jacobian-vector product for deep networks. Balestriero, R.; and Baraniuk, R. arXiv preprint arXiv:2104.00219. 2021.
link bibtex

@article{balestriero2021fast,
  title={Fast Jacobian-vector product for deep networks},
  author={Balestriero, Randall and Baraniuk, Richard},
  journal={arXiv preprint arXiv:2104.00219},
  year={2021}
}

Max-Affine Splines Insights Into Deep Learning (PhD Thesis). Balestriero, R. Ph.D. Thesis, Rice University, 2021.
link bibtex

@phdthesis{balestriero2021max,
  title={Max-Affine Splines Insights Into Deep Learning (PhD Thesis)},
  author={Balestriero, Randall},
  year={2021},
  school={Rice University}
}

NeuroView: Explainable Deep Network Decision Making. Barberan, C.; Balestriero, R.; and Baraniuk, R. G arXiv preprint arXiv:2110.07778. 2021.
link bibtex

@article{barberan2021neuroview,
  title={NeuroView: Explainable Deep Network Decision Making},
  author={Barberan, CJ and Balestriero, Randall and Baraniuk, Richard G},
  journal={arXiv preprint arXiv:2110.07778},
  year={2021}
}

MaGNET: Uniform sampling from deep generative network manifolds without retraining. Humayun, A. I.; Balestriero, R.; and Baraniuk, R. In International Conference on Learning Representations, 2021.
link bibtex

@inproceedings{humayun2021magnet,
  title={MaGNET: Uniform sampling from deep generative network manifolds without retraining},
  author={Humayun, Ahmed Imtiaz and Balestriero, Randall and Baraniuk, Richard},
  booktitle={International Conference on Learning Representations},
  year={2021}
}

Learning in high dimension always amounts to extrapolation. Balestriero, R.; Pesenti, J.; and LeCun, Y. arXiv preprint arXiv:2110.09485. 2021.
link bibtex

@article{balestriero2021learning,
  title={Learning in high dimension always amounts to extrapolation},
  author={Balestriero, Randall and Pesenti, Jerome and LeCun, Yann},
  journal={arXiv preprint arXiv:2110.09485},
  year={2021}
}

Anatomy of continuous Mars SEIS and pressure data from unsupervised learning. Barkaoui, S.; Lognonné, P.; Kawamura, T.; Stutzmann, É.; Seydoux, L.; de Hoop, M. V; Balestriero, R.; Scholz, J.; Sainton, G.; Plasman, M.; and others Bulletin of the Seismological Society of America, 111(6): 2964–2981. 2021.
link bibtex

@article{barkaoui2021anatomy,
  title={Anatomy of continuous Mars SEIS and pressure data from unsupervised learning},
  author={Barkaoui, Salma and Lognonn{\'e}, Philippe and Kawamura, Taichi and Stutzmann, {\'E}l{\'e}onore and Seydoux, L{\'e}onard and de Hoop, Maarten V and Balestriero, Randall and Scholz, John-Robert and Sainton, Gr{\'e}gory and Plasman, Matthieu and others},
  journal={Bulletin of the Seismological Society of America},
  volume={111},
  number={6},
  pages={2964--2981},
  year={2021},
  publisher={Seismological Society of America}
}

Recurrent scattering network detects metastable behavior in polyphonic seismo-volcanic signals for volcano eruption forecasting. Rodrı́guez, Ángel Bueno; Balestriero, R.; De Angelis, S.; Benı́tez, M Carmen; Zuccarello, L.; Baraniuk, R.; Ibáñez, J. M; and de Hoop, M. V IEEE Transactions on Geoscience and Remote Sensing, 60: 1–23. 2021.
link bibtex

@article{rodriguez2021recurrent,
  title={Recurrent scattering network detects metastable behavior in polyphonic seismo-volcanic signals for volcano eruption forecasting},
  author={Rodr{\'\i}guez, {\'A}ngel Bueno and Balestriero, Randall and De Angelis, Silvio and Ben{\'\i}tez, M Carmen and Zuccarello, Luciano and Baraniuk, Richard and Ib{\'a}{\~n}ez, Jes{\'u}s M and de Hoop, Maarten V},
  journal={IEEE Transactions on Geoscience and Remote Sensing},
  volume={60},
  pages={1--23},
  year={2021},
  publisher={IEEE}
}

High fidelity visualization of what your self-supervised representation knows about. Bordes, F.; Balestriero, R.; and Vincent, P. arXiv preprint arXiv:2112.09164. 2021.
link bibtex

@article{bordes2021high,
  title={High fidelity visualization of what your self-supervised representation knows about},
  author={Bordes, Florian and Balestriero, Randall and Vincent, Pascal},
  journal={arXiv preprint arXiv:2112.09164},
  year={2021}
}

Learning the signature of slow-slip events and slow earthquakes from seismic and geodetic data. Seydoux, L.; Steinmann, R.; Campillo, M.; De Hoop, M.; and Balestriero, R. In AGU Fall Meeting Abstracts, volume 2021, pages S35C–0240, 2021.
link bibtex

@inproceedings{seydoux2021learning,
  title={Learning the signature of slow-slip events and slow earthquakes from seismic and geodetic data},
  author={Seydoux, Leonard and Steinmann, Rene and Campillo, Michel and De Hoop, Maarten and Balestriero, Randall},
  booktitle={AGU Fall Meeting Abstracts},
  volume={2021},
  pages={S35C--0240},
  year={2021}
}

Max-affine spline insights into deep network pruning. Balestriero, R.; You, H.; Lu, Z.; Kou, Y.; Shi, H.; Lin, Y.; and Baraniuk, R. . 2021.
link bibtex

@article{balestriero2021max,
  title={Max-affine spline insights into deep network pruning},
  author={Balestriero, Randall and You, Haoran and Lu, Zhihan and Kou, Yutong and Shi, Huihong and Lin, Yingyan and Baraniuk, Richard},
  year={2021}
}

2020 (12)

Mad max: Affine spline insights into deep learning. Balestriero, R.; and Baraniuk, R. G Proceedings of the IEEE,1–24. 2020.
link bibtex

@article{balestriero2020mad,
  title={Mad max: Affine spline insights into deep learning},
  author={Balestriero, Randall and Baraniuk, Richard G},
  journal={Proceedings of the IEEE},
  pages={1--24},
  year={2020},
  publisher={IEEE}
}

Max-affine spline insights into deep generative networks. Balestriero, R.; Paris, S.; and Baraniuk, R. arXiv preprint arXiv:2002.11912. 2020.
link bibtex

@article{balestriero2020max,
  title={Max-affine spline insights into deep generative networks},
  author={Balestriero, Randall and Paris, Sebastien and Baraniuk, Richard},
  journal={arXiv preprint arXiv:2002.11912},
  year={2020}
}

Symjax: symbolic cpu/gpu/tpu programming. Balestriero, R. arXiv preprint arXiv:2005.10635. 2020.
link bibtex

@article{balestriero2020symjax,
  title={Symjax: symbolic cpu/gpu/tpu programming},
  author={Balestriero, Randall},
  journal={arXiv preprint arXiv:2005.10635},
  year={2020}
}

Analytical Probability Distributions and EM-Learning for Deep Generative Networks. Balestriero, R.; Paris, S.; and Baraniuk, R. G In Neural Information Processing Systems, volume 33, 2020.
link bibtex

@inproceedings{balestriero2020analytical,
  title={Analytical Probability Distributions and EM-Learning for Deep Generative Networks},
  author={Balestriero, Randall and Paris, Sebastien and Baraniuk, Richard G},
  booktitle={Neural Information Processing Systems},
  volume={33},
  year={2020}
}

The recurrent neural tangent kernel. Alemohammad, S.; Wang, Z.; Balestriero, R.; and Baraniuk, R. In International Conference on Learning Representations, 2020.
link bibtex

@inproceedings{alemohammad2020recurrent,
  title={The recurrent neural tangent kernel},
  author={Alemohammad, Sina and Wang, Zichao and Balestriero, Randall and Baraniuk, Richard},
  booktitle={International Conference on Learning Representations},
  year={2020}
}

Ensembles of generative adversarial networks for disconnected data. Luzi, L.; Balestriero, R.; and Baraniuk, R. G arXiv preprint arXiv:2006.14600. 2020.
link bibtex

@article{luzi2020ensembles,
  title={Ensembles of generative adversarial networks for disconnected data},
  author={Luzi, Lorenzo and Balestriero, Randall and Baraniuk, Richard G},
  journal={arXiv preprint arXiv:2006.14600},
  year={2020}
}

Universal frame thresholding. Cosentino, R.; Balestriero, R.; Baraniuk, R. G; and Aazhang, B. IEEE Signal Processing Letters, 27: 1115–1119. 2020.
link bibtex

@article{cosentino2020universal,
  title={Universal frame thresholding},
  author={Cosentino, Romain and Balestriero, Randall and Baraniuk, Richard G and Aazhang, Behnaam},
  journal={IEEE Signal Processing Letters},
  volume={27},
  pages={1115--1119},
  year={2020},
  publisher={IEEE}
}

Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning. Seydoux, L.; Balestriero, R.; Poli, P.; Hoop, M. d.; Campillo, M.; and Baraniuk, R. Nature communications, 11(1): 3972. 2020.
link bibtex

@article{seydoux2020clustering,
  title={Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning},
  author={Seydoux, L{\'e}onard and Balestriero, Randall and Poli, Piero and Hoop, Maarten de and Campillo, Michel and Baraniuk, Richard},
  journal={Nature communications},
  volume={11},
  number={1},
  pages={3972},
  year={2020},
  publisher={Nature Publishing Group UK London}
}

Scalable neural tangent kernel of recurrent architectures. Alemohammad, S.; Balestriero, R.; Wang, Z.; and Baraniuk, R. G arXiv preprint arXiv:2012.04859. 2020.
link bibtex

@article{alemohammad2020scalable,
  title={Scalable neural tangent kernel of recurrent architectures},
  author={Alemohammad, Sina and Balestriero, Randall and Wang, Zichao and Baraniuk, Richard G},
  journal={arXiv preprint arXiv:2012.04859},
  year={2020}
}

Sparse Multi-Family Deep Scattering Network. Cosentino, R.; and Balestriero, R. arXiv preprint arXiv:2012.07662. 2020.
link bibtex

@article{cosentino2020sparse,
  title={Sparse Multi-Family Deep Scattering Network},
  author={Cosentino, Romain and Balestriero, Randall},
  journal={arXiv preprint arXiv:2012.07662},
  year={2020}
}

Interpretable Image Clustering via Diffeomorphism-Aware K-Means. Cosentino, R.; Balestriero, R.; Bahroun, Y.; Sengupta, A.; Baraniuk, R.; and Aazhang, B. arXiv preprint arXiv:2012.09743. 2020.
link bibtex

@article{cosentino2020interpretable,
  title={Interpretable Image Clustering via Diffeomorphism-Aware K-Means},
  author={Cosentino, Romain and Balestriero, Randall and Bahroun, Yanis and Sengupta, Anirvan and Baraniuk, Richard and Aazhang, Behnaam},
  journal={arXiv preprint arXiv:2012.09743},
  year={2020}
}

Enhanced recurrent neural tangent kernels for non-time-series data. Alemohammad, S.; Balestriero, R.; Wang, Z.; and Baraniuk, R. arXiv preprint arXiv:2012.04859. 2020.
link bibtex

@article{alemohammad2020enhanced,
  title={Enhanced recurrent neural tangent kernels for non-time-series data},
  author={Alemohammad, Sina and Balestriero, Randall and Wang, Zichao and Baraniuk, Richard},
  journal={arXiv preprint arXiv:2012.04859},
  year={2020}
}

2019 (5)

The geometry of deep networks: Power diagram subdivision. Balestriero, R.; Cosentino, R.; Aazhang, B.; and Baraniuk, R. In Advances in Neural Information Processing Systems, volume 32, pages 15832–15841, 2019.
link bibtex

@inproceedings{balestriero2019geometry,
  title={The geometry of deep networks: Power diagram subdivision},
  author={Balestriero, Randall and Cosentino, Romain and Aazhang, Behnaam and Baraniuk, Richard},
  booktitle={Advances in Neural Information Processing Systems},
  volume={32},
  pages={15832--15841},
  year={2019}
}

Implicit rugosity regularization via data augmentation. LeJeune, D.; Balestriero, R.; Javadi, H.; and Baraniuk, R. G arXiv preprint arXiv:1905.11639. 2019.
link bibtex

@article{lejeune2019implicit,
  title={Implicit rugosity regularization via data augmentation},
  author={LeJeune, Daniel and Balestriero, Randall and Javadi, Hamid and Baraniuk, Richard G},
  journal={arXiv preprint arXiv:1905.11639},
  year={2019}
}

Seismic signals and noises clustering with unsupervised deep representation learning. Seydoux, L.; Balestriero, R.; Poli, P.; De Hoop, M. V; Baraniuk, R.; and Campillo, M. In AGU Fall Meeting Abstracts, volume 2019, pages S52A–04, 2019.
link bibtex

@inproceedings{seydoux2019seismic,
  title={Seismic signals and noises clustering with unsupervised deep representation learning},
  author={Seydoux, Leonard and Balestriero, Randall and Poli, Piero and De Hoop, Maarten V and Baraniuk, Richard and Campillo, Michel},
  booktitle={AGU Fall Meeting Abstracts},
  volume={2019},
  pages={S52A--04},
  year={2019}
}

Wavelet learning by adaptive hermite cubic splines applied to bioacoustic chirps. Balestriero, R.; and Glotin, H. In OCEANS 2019-Marseille, pages 1–5, 2019. IEEE
link bibtex

@inproceedings{balestriero2019wavelet,
  title={Wavelet learning by adaptive hermite cubic splines applied to bioacoustic chirps},
  author={Balestriero, Randall and Glotin, Herv{\'e}},
  booktitle={OCEANS 2019-Marseille},
  pages={1--5},
  year={2019},
  organization={IEEE}
}

A GOODNESS OF FIT MEASURE FOR GENERATIVE NETWORKS. Luzi, L.; Balestriero, R.; and Baraniuk, R. . 2019.
link bibtex

@article{luzi2019goodness,
  title={A GOODNESS OF FIT MEASURE FOR GENERATIVE NETWORKS},
  author={Luzi, Lorenzo and Balestriero, Randall and Baraniuk, Richard},
  year={2019}
}

2018 (7)

Semi-supervised learning enabled by multiscale deep neural network inversion. Balestriero, R.; Glotin, H.; and Baraniuk, R. arXiv preprint arXiv:1802.10172. 2018.
link bibtex

@article{balestriero2018semi,
  title={Semi-supervised learning enabled by multiscale deep neural network inversion},
  author={Balestriero, Randall and Glotin, Herv{\'e} and Baraniuk, Richard},
  journal={arXiv preprint arXiv:1802.10172},
  year={2018}
}

A spline theory of deep learning. Balestriero, R.; and Baraniuk, R. In International Conference on Machine Learning, pages 374–383, 2018. PMLR
link bibtex

@inproceedings{balestriero2018spline,
  title={A spline theory of deep learning},
  author={Balestriero, Randall and Baraniuk, Richard},
  booktitle={International Conference on Machine Learning},
  pages={374--383},
  year={2018},
  organization={PMLR}
}

Spline filters for end-to-end deep learning. Balestriero, R.; Cosentino, R.; Glotin, H.; and Baraniuk, R. In International conference on machine learning, pages 364–373, 2018. PMLR
link bibtex

@inproceedings{balestriero2018spline,
  title={Spline filters for end-to-end deep learning},
  author={Balestriero, Randall and Cosentino, Romain and Glotin, Herv{\'e} and Baraniuk, Richard},
  booktitle={International conference on machine learning},
  pages={364--373},
  year={2018},
  organization={PMLR}
}

Deep learning for ethoacoustical mapping: application to a single Cachalot long term recording on joint observatories in Vancouver Island. Glotin, H.; Spong, P.; Symonds, H.; Roger, V.; Balestriero, R.; Ferrari, M.; Poupard, M.; Towers, J.; Veirs, S.; Marxer, R.; and others The Journal of the Acoustical Society of America, 144(3_Supplement): 1776–1777. 2018.
link bibtex

@article{glotin2018deep,
  title={Deep learning for ethoacoustical mapping: application to a single Cachalot long term recording on joint observatories in Vancouver Island},
  author={Glotin, Herve and Spong, Paul and Symonds, Helena and Roger, Vincent and Balestriero, Randall and Ferrari, Maxence and Poupard, Marion and Towers, Jared and Veirs, Scott and Marxer, Ricard and others},
  journal={The Journal of the Acoustical Society of America},
  volume={144},
  number={3\_Supplement},
  pages={1776--1777},
  year={2018},
  publisher={AIP Publishing}
}

A max-affine spline perspective of recurrent neural networks. Wang, Z.; Balestriero, R.; and Baraniuk, R. In International Conference on Learning Representations, 2018.
link bibtex

@inproceedings{wang2018max,
  title={A max-affine spline perspective of recurrent neural networks},
  author={Wang, Zichao and Balestriero, Randall and Baraniuk, Richard},
  booktitle={International Conference on Learning Representations},
  year={2018}
}

From hard to soft: Understanding deep network nonlinearities via vector quantization and statistical inference. Balestriero, R.; and Baraniuk, R. G In International Conference on Learning Representations, 2018.
link bibtex

@inproceedings{balestriero2018hard,
  title={From hard to soft: Understanding deep network nonlinearities via vector quantization and statistical inference},
  author={Balestriero, Randall and Baraniuk, Richard G},
  booktitle={International Conference on Learning Representations},
  year={2018}
}

A spline theory of deep networks. Baraniuk, R. G; and Balestriero, R. In 35th International Conference on Machine Learning, ICML 2018, pages 646–660, 2018. International Machine Learning Society (IMLS)
link bibtex

@inproceedings{baraniuk2018spline,
  title={A spline theory of deep networks},
  author={Baraniuk, Richard G and Balestriero, Randall},
  booktitle={35th International Conference on Machine Learning, ICML 2018},
  pages={646--660},
  year={2018},
  organization={International Machine Learning Society (IMLS)}
}

2017 (6)

Neural decision trees. Balestriero, R. arXiv preprint arXiv:1702.07360. 2017.
link bibtex

@article{balestriero2017neural,
  title={Neural decision trees},
  author={Balestriero, Randall},
  journal={arXiv preprint arXiv:1702.07360},
  year={2017}
}

Linear time complexity deep Fourier scattering network and extension to nonlinear invariants. Balestriero, R.; and Glotin, H. arXiv preprint arXiv:1707.05841. 2017.
link bibtex

@article{balestriero2017linear,
  title={Linear time complexity deep Fourier scattering network and extension to nonlinear invariants},
  author={Balestriero, Randall and Glotin, Herv{\'e}},
  journal={arXiv preprint arXiv:1707.05841},
  year={2017}
}

Fast chirplet transform injects priors in deep learning of animal calls and speech. Glotin, H.; Ricard, J.; and Balestriero, R. In International Conference on Learning Representations Workshop, 2017.
link bibtex

@inproceedings{glotin2017fast,
  title={Fast chirplet transform injects priors in deep learning of animal calls and speech},
  author={Glotin, Herv{\'e} and Ricard, Julien and Balestriero, Randall},
  booktitle={International Conference on Learning Representations Workshop},
  year={2017}
}

Multiscale Residual Mixture of PCA: Dynamic Dictionaries for Optimal Basis Learning. Balestriero, R. arXiv preprint arXiv:1707.05840. 2017.
link bibtex

@article{balestriero2017multiscale,
  title={Multiscale Residual Mixture of PCA: Dynamic Dictionaries for Optimal Basis Learning},
  author={Balestriero, Randall},
  journal={arXiv preprint arXiv:1707.05840},
  year={2017}
}

Sparse Deep Scattering Croisé Network. Cosentino, R.; Balestriero, R.; Baraniuk, R.; and Patel, A. . 2017.
link bibtex

@article{cosentino2017sparse,
  title={Sparse Deep Scattering Crois{\'e} Network},
  author={Cosentino, Romain and Balestriero, Randall and Baraniuk, Richard and Patel, Ankit},
  year={2017}
}

Adaptive Partitioning Spline Neural Networks: Template Matching, Memorization, Inhibitor Connections, Inversion, Semi-Sup, Topology Search,... Balestriero, R.; and Baraniuk, R. G Topology Search,..., arxiv, 1710. 2017.
link bibtex

@article{balestriero2017adaptive,
  title={Adaptive Partitioning Spline Neural Networks: Template Matching, Memorization, Inhibitor Connections, Inversion, Semi-Sup, Topology Search,...},
  author={Balestriero, Randall and Baraniuk, Richard G},
  journal={Topology Search,..., arxiv},
  volume={1710},
  year={2017}
}

2016 (2)

Robust unsupervised transient detection with invariant representation based on the scattering network. Balestriero, R.; and Aazhang, B. arXiv preprint arXiv:1611.07850. 2016.
link bibtex

@article{balestriero2016robust,
  title={Robust unsupervised transient detection with invariant representation based on the scattering network},
  author={Balestriero, Randall and Aazhang, Behnaam},
  journal={arXiv preprint arXiv:1611.07850},
  year={2016}
}

Best basis selection using sparsity driven multi-family wavelet transform. Cosentino, R.; Balestriero, R.; and Aazhang, B. In 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pages 252–256, 2016. IEEE
link bibtex

@inproceedings{cosentino2016best,
  title={Best basis selection using sparsity driven multi-family wavelet transform},
  author={Cosentino, Romain and Balestriero, Randall and Aazhang, Behnaam},
  booktitle={2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP)},
  pages={252--256},
  year={2016},
  organization={IEEE}
}

2015 (2)

Enhanced feature extraction using the morlet transform on 1 mhz recordings reveals the complex nature of amazon river dolphin (inia geoffrensis) clicks. Trone, M.; Glotin, H.; Balestriero, R.; and Bonnett, D. E The Journal of the Acoustical Society of America, 138(3_Supplement): 1904–1904. 2015.
link bibtex

@article{trone2015enhanced,
  title={Enhanced feature extraction using the morlet transform on 1 mhz recordings reveals the complex nature of amazon river dolphin (inia geoffrensis) clicks},
  author={Trone, Marie and Glotin, Herv{\'e} and Balestriero, Randall and Bonnett, David E},
  journal={The Journal of the Acoustical Society of America},
  volume={138},
  number={3\_Supplement},
  pages={1904--1904},
  year={2015},
  publisher={AIP Publishing}
}

Scattering decomposition for massive signal classification: from theory to fast algorithm and implementation with validation on international bioacoustic benchmark. Balestriero, R.; and Glotin, H. In 2015 IEEE International Conference on Data Mining Workshop (ICDMW), pages 753–761, 2015. IEEE
link bibtex

@inproceedings{balestriero2015scattering,
  title={Scattering decomposition for massive signal classification: from theory to fast algorithm and implementation with validation on international bioacoustic benchmark},
  author={Balestriero, Randall and Glotin, Herv{\'e}},
  booktitle={2015 IEEE International Conference on Data Mining Workshop (ICDMW)},
  pages={753--761},
  year={2015},
  organization={IEEE}
}

2014 (2)

All clicks are not created equally: Variations in high-frequency acoustic signal parameters of the Amazon river dolphin (Inia geoffrensis). Trone, M.; Balestriero, R.; Glotin, H.; and David, B. E The Journal of the Acoustical Society of America, 136(4_Supplement): 2217–2217. 2014.
link bibtex

@article{trone2014all,
  title={All clicks are not created equally: Variations in high-frequency acoustic signal parameters of the Amazon river dolphin (Inia geoffrensis)},
  author={Trone, Marie and Balestriero, Randall and Glotin, Herv{\'e} and David, Bonnett E},
  journal={The Journal of the Acoustical Society of America},
  volume={136},
  number={4\_Supplement},
  pages={2217--2217},
  year={2014},
  publisher={AIP Publishing}
}

Heterogeneity of Amazon River dolphin high-frequency clicks: Current Odontoceti bioacoustic terminology in need of standardization. Trone, M.; Glotin, H.; Balestriero, R.; Bonnett, D. E; and Blakefield, J. In Proceedings of Meetings on Acoustics, volume 22, 2014. AIP Publishing
link bibtex

@inproceedings{trone2014heterogeneity,
  title={Heterogeneity of Amazon River dolphin high-frequency clicks: Current Odontoceti bioacoustic terminology in need of standardization},
  author={Trone, Marie and Glotin, Herv{\'e} and Balestriero, Randall and Bonnett, David E and Blakefield, Jerry},
  booktitle={Proceedings of Meetings on Acoustics},
  volume={22},
  number={1},
  year={2014},
  organization={AIP Publishing}
}

2013 (1)

Gabor scalogram extracts dolphin click formants. Trone, M.; Balestriero, R.; and Glotin, H. In Proc. 1st workshop Neural Information Processing Scaled for Bioacoustics-from neurons to Big Data-NIPS4B. NIPS4B, 2013.
link bibtex

@inproceedings{trone2013gabor,
  title={Gabor scalogram extracts dolphin click formants},
  author={Trone, Marie and Balestriero, Randall and Glotin, Herv{\'e}},
  booktitle={Proc. 1st workshop Neural Information Processing Scaled for Bioacoustics-from neurons to Big Data-NIPS4B. NIPS4B},
  year={2013}
}

undefined (7)

Optimal Binary Classifier Hierarchy for Large Scale Regression Problems with Validation on Stock Market Volumes Forecasting. BALESTRIERO, R. . .
link bibtex

@article{balestrierooptimal,
  title={Optimal Binary Classifier Hierarchy for Large Scale Regression Problems with Validation on Stock Market Volumes Forecasting},
  author={BALESTRIERO, Randall}
}

FAST CHIRPLET TRANSFORM ENHANCES CNN-BASED AUDIO CLASSIFIER ON SMALL DATA. Glotin, H.; La Garde, F.; Ricard, J.; and Balestriero, R. . .
link bibtex

@article{glotinfast,
  title={FAST CHIRPLET TRANSFORM ENHANCES CNN-BASED AUDIO CLASSIFIER ON SMALL DATA},
  author={Glotin, Herv{\'e} and La Garde, France and Ricard, Julien and Balestriero, Randall}
}

Deep Q-Network Research Project. Balestriero, R.; and Cosentino, R. . .
link bibtex

@article{balestrierodeep,
  title={Deep Q-Network Research Project},
  author={Balestriero, Randall and Cosentino, Romain}
}

GPU Implementation of Probabilistic Mixture Models for High Dimensional Dataset. COSENTINO, R.; and BALESTRIERO, R. . .
link bibtex

@article{cosentinogpu,
  title={GPU Implementation of Probabilistic Mixture Models for High Dimensional Dataset},
  author={COSENTINO, Romain and BALESTRIERO, Randall}
}

6.1 Gabor Scalogram Reveals Formants in High-Frequency Dolphin Clicks. Trone, M.; Balestriero, R.; and Glotin, H. . .
link bibtex

@article{trone6,
  title={6.1 Gabor Scalogram Reveals Formants in High-Frequency Dolphin Clicks},
  author={Trone, Marie and Balestriero, Randall and Glotin, Herv{\'e}}
}

FAIR-Ensemble: Homogeneous Deep Ensembling Naturally Attenuates Disparate Group Performances. Ko, W.; D'souza, D.; Nguyen, K.; Balestriero, R.; and Hooker, S. . .
link bibtex

@article{kofair,
  title={FAIR-Ensemble: Homogeneous Deep Ensembling Naturally Attenuates Disparate Group Performances},
  author={Ko, Wei-Yin and D'souza, Daniel and Nguyen, Karina and Balestriero, Randall and Hooker, Sara}
}

Scaling Vision-Language Models Does Not Improve Relational Understanding: The Right Learning Objective Helps. Al-Tahan, H.; Garrido, Q.; Balestriero, R.; Bouchacourt, D.; Hazirbas, C.; Ibrahim, M.; and FAIR, M. . .
link bibtex

@article{alscaling,
  title={Scaling Vision-Language Models Does Not Improve Relational Understanding: The Right Learning Objective Helps},
  author={Al-Tahan, Haider and Garrido, Quentin and Balestriero, Randall and Bouchacourt, Diane and Hazirbas, Caner and Ibrahim, Mark and FAIR, Meta}
}